X-Cluster, A Novel and Efficient Approach towards Unsupervised Learning

Data mining is the extraction of knowledge from large amount of data. It is an essential step of knowledge discovery in databases or KDD process. One of the popular data mining techniques is clustering in which different objects are assigned to groups (clusters) depending on their characteristics. It is a type of unsupervised learning which helps in pattern recognition so that objects in one group behave in a similar manner and are different from the other. The novelty of the paper comes from the fact that it shows a way to perform Clustering using Microsoft Excel files which are used to store the data sets. KD - trees are also used to speed up the Clustering process. A new tool is devised which has various advantages over the most widely used tool WEKA. This paper aims at showing that Microsoft Excel is a great tool as far as technical learning is concerned for the fact that, it is very easy and successful in providing the first hand exposure to a novice user.